Tailscale built Aperture, its customer-facing AI model router, on Vercel AI Gateway and Vercel Sandbox, giving customers access to hundreds of AI models routed through their private tailnet network. R…
Vercel increased storage for every Vercel Sandbox to 64 GB, up from 32 GB, according to a changelog post by Andy Waller and Luke Phillips-Sheard. The change applies to sandboxes created from a Vercel …
Vercel's AI SDK harness layer now supports GitHub Copilot through the official @ai-sdk/harness-github-copilot adapter, letting applications run different coding agents through the same HarnessAgent in…
Vercel is offering Tako Search free exclusively on its AI Gateway through September 30th. Tako Search is a model-agnostic search tool that works with any model on AI Gateway, combining a curated knowl…
Vercel now supports building and deploying long-running, tool-using agents with the OpenAI Agents API, with OpenAI managing the agent loop and session state while Vercel hosts the application and conn…
Vercel has released an experimental beta of DeepSeek V4.1 Flash, available through its AI Gateway, with pricing set at $0.22 per 1 million input tokens and $0.66 per 1 million output tokens, and the b…
Vercel has released version 59.6.0 of its CLI, adding a new `vercel changelog` command that lets users and coding agents read and search the Vercel changelog feed directly from the terminal. The comma…
DeepSeek V4.1 Flash is now available on Vercel's AI Gateway with native image understanding, accepting text and images in the same request. The model offers a 1 million token context window, responses…
Vercel's deployment step is now about 10% faster, saving one second on average and up to 12 seconds for large applications, according to a changelog by Ali Smesseim, Tim Caswell, Steven Salat, and Jav…
Vercel's AI Gateway now offers OpenAI's GPT Image 2.5 Flare and GPT Image 2.5 Sunburst models, accessible as openai/gpt-image-2.5-flare and openai/gpt-image-2.5-sunburst. Flare is optimized for faster…
Vercel's AI Gateway now offers Ling 3.0 Flash Sante, a health-focused Mixture-of-Experts model from inclusionAI with 124B total parameters and about 5.1B active per token, free through October 4. The …
OpenAI's GPT 6 Astra model is now available on Vercel's AI Gateway, enabling developers to integrate the model for long-running agentic tasks such as software engineering, computer and browser use, an…
Cursor Cloud Agents can now run in Vercel Sandbox, replacing Cursor's hosted machines with isolated Firecracker microVMs for each agent request. The integration uses Vercel Functions and Vercel Workfl…
Vercel's AI Gateway is offering GLM-5.3 at a 50% discount through Tuesday, September 8, in partnership with DigitalOcean, using the promo name 'zai/glm-5.3-promo-50'. The promo routes only to DigitalO…
Vercel's AI Gateway now offers Google's Gemini 3.8 Flash model, priced 50% off through December 31st, with a 1M token context window, multimodal input, and 65,536-token maximum output. The model impro…
Meta's Muse Spark 1.3 is now available on Vercel's AI Gateway in standard and contributor pricing tiers, featuring a 1M token context window and text, image, and PDF input. The model improves on prior…
Anthropic's Claude Fable 5.1 is now available on Vercel's AI Gateway, featuring improvements for long, multi-stage tasks like agentic coding and research, with cybersecurity and biology safety classif…
Vercel's AI Gateway now offers Qwen 3.8 Max 0902, a new snapshot of Alibaba's Qwen 3.8 Max model, with improvements in coding on larger projects, long-horizon unsupervised work, agent runs, and vision…
Vercel has introduced per-user budgets on its AI Gateway, allowing teams to set dollar spending limits for each user, covering spend from all API keys and app tokens attributed to that user. Once a us…
Vercel's AI SDK harness layer now supports fx, its lightweight open-source coding agent, via the official @ai-sdk/harness-fx adapter, which connects over the Agent Client Protocol using @ai-sdk/harnes…